whisper-small-finetuned-iwslt-irish-welsh-curriculum-b-no-frozen-decoder
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 5.8234
- Wer: 102.0329
- Bleu: 1.1306
- Chrf++: 13.4640
- Comet: 0.4158
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- training_steps: 5000
- mixed_precision_training: Native AMP
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Bleu | Chrf++ | Comet |
|---|---|---|---|---|---|---|---|
| 1.921 | 2.6709 | 1250 | 4.9240 | 111.1131 | 0.9500 | 13.6263 | 0.4177 |
| 1.5352 | 5.3419 | 2500 | 5.3364 | 109.4416 | 1.0718 | 13.1196 | 0.4192 |
| 1.4693 | 8.0128 | 3750 | 5.5399 | 103.2526 | 1.0332 | 13.4968 | 0.4194 |
| 1.4248 | 10.6838 | 5000 | 5.8234 | 102.0329 | 1.1306 | 13.4640 | 0.4158 |
Framework versions
- Transformers 4.52.0
- Pytorch 2.11.0+cu128
- Datasets 2.21.0
- Tokenizers 0.21.4